Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is \textit{hard attention}, which uses only relevant portions of the image. However, training hard attention models with only class label supervision is challenging, and hard attention has proved difficult to scale to complex datasets. Here, we propose a novel hard attention model, which we term Saccader. Key to Saccader is a pretraining step that requires only class labels and provides initial attention locations for policy gradient optimization. Our best models narrow the gap to common ImageNet baselines, achieving $75\%$ top-1 and $91\%$ top-5 while attending to less than one-third of the image.
GRPO with State Mutations: Improving LLM-Based Hardware Test Plan Generation
Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA（麻省理工学院电子工程与计算机科学系）；NVIDIA Research, Austin, TX（NVIDIA研究部）；NVIDIA Research, Taiwan（NVIDIA台湾研究部）；NVIDIA Research, Santa Clara, CA（NVIDIA圣克拉拉研究部）
Stanford University（斯坦福大学）；University of Washington（华盛顿大学）；Meta AI；University College London（伦敦大学学院）；Cohere（Cohere公司）
Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse. One common solution is to use intrinsic rewards to encourage agents to explore their environment. However, recent intrinsic exploration methods often use state-based novelty measures which reward low-level exploration and may not scale to domains requiring more abstract skills. Instead, we explore natural language as a general medium for highlighting relevant abstractions in an environment. Unlike previous work, we evaluate whether language can improve over existing exploration methods by directly extend…
University of Toronto（多伦多大学）；Vector Institute（矢量研究院）；Google Brain（谷歌大脑）
We present a new technique for learning visual-semantic embeddings for cross-modal retrieval. Inspired by hard negative mining, the use of hard negatives in structured prediction, and ranking loss functions, we introduce a simple change to common loss functions used for multi-modal embeddings. That, combined with fine-tuning and use of augmented data, yields significant gains in retrieval performance. We showcase our approach, VSE++, on MS-COCO and Flickr30K datasets, using ablation studies and comparisons with existing methods. On MS-COCO our approach outperforms state-of-the-art methods by 8…
An important component of unsupervised learning by instance-based discrimination is a memory bank for storing a feature representation for each training sample in the dataset. In this paper, we introduce 3 improvements to the vanilla memory bank-based formulation which brings massive accuracy gains: (a) Large mini-batch: we pull multiple augmentations for each sample within the same batch and show that this leads to better models and enhanced memory bank updates. (b) Consistency: we enforce the logits obtained by different augmentations of the same sample to be close without trying to enforce …
Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theoretically, adversarial perturbation in untargeted attacks can be added along arbitrary directions and the predicted labels of untargeted attacks should be unpredictable. However, we find that the naturally imbalanced inter-class semantic similarity makes those hard-class pairs become virtual targets of each other. This study investigates the impact of such closely-coupled classes on adversarial attacks and develops a s…
In the thesis we consider the problem of local feature descriptor learning for wide baseline stereo focusing on the HardNet descriptor, which is close to state-of-the-art. AMOS Patches dataset is introduced, which improves robustness to illumination and appearance changes. It is based on registered images from selected cameras from the AMOS dataset. We provide recommendations on the patch dataset creation process and evaluate HardNet trained on data of different modalities. We also introduce a dataset combination and reduction methods, that allow comparable performance on a significantly small…
Sunnybrook Research Institute（森尼布鲁克研究所）；University of Toronto（多伦多大学）
Self-supervised learning (SSL) has recently shown tremendous potential to learn generic visual representations useful for many image analysis tasks. Despite their notable success, the existing SSL methods fail to generalize to downstream tasks when the number of labeled training instances is small or if the domain shift between the transfer domains is significant. In this paper, we attempt to improve self-supervised pretrained representations through the lens of curriculum learning by proposing a hardness-aware dynamic curriculum learning (HaDCL) approach. To improve the robustness and general…
Tencent（腾讯）；Michigan State University（密歇根州立大学）；Xiamen University（厦门大学）
Large facial variations are the main challenge in face recognition. To this end, previous variation-specific methods make full use of task-related prior to design special network losses, which are typically not general among different tasks and scenarios. In contrast, the existing generic methods focus on improving the feature discriminability to minimize the intra-class distance while maximizing the interclass distance, which perform well on easy samples but fail on hard samples. To improve the performance on those hard samples for general tasks, we propose a novel Distribution Distillation L…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Adversarial training (AT) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the final robustness of models during AT, that is, the so-called hard examples that can be attacked easily exhibit more influence than robust examples on the final robustness. Therefore, guaranteeing the robustness of hard examples is crucial for improving the final robustness of the model. However, defining effective heuristics to search for hard examples is still difficult. In this article, inspired by the information …
Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial training that trains the model with adversarially perturbed samples instead of original ones. Various methods have been developed over recent years to improve adversarial training such as data augmentation or modifying training attacks. In this work, we examine the same problem from a new data-centric perspective. For this purpose, we first demonstrate that the ex…
Improving object detectors against occlusion, blur and noise is a critical step to deploy detectors in real applications. Since it is not possible to exhaust all image defects through data collection, many researchers seek to generate hard samples in training. The generated hard samples are either images or feature maps with coarse patches dropped out in the spatial dimensions. Significant overheads are required in training the extra hard samples and/or estimating drop-out patches using extra network branches. In this paper, we improve object detectors using a highly efficient and fine-grain m…
Microsoft AI（微软人工智能）；Microsoft Research（微软研究院）；University of Maryland, College Park（马里兰大学学院市分校）
Existing meta-learners primarily focus on improving the average task accuracy across multiple episodes. Different episodes, however, may vary in hardness and quality leading to a wide gap in the meta-learner's performance across episodes. Understanding this issue is particularly critical in industrial few-shot settings, where there is limited control over test episodes as they are typically uploaded by end-users. In this paper, we empirically analyse the behaviour of meta-learners on episodes of varying hardness across three standard benchmark datasets: CIFAR-FS, mini-ImageNet, and tiered-Imag…
Visual Semantic Embedding (VSE) aims to extract the semantics of images and their descriptions, and embed them into the same latent space for cross-modal information retrieval. Most existing VSE networks are trained by adopting a hard negatives loss function which learns an objective margin between the similarity of relevant and irrelevant image-description embedding pairs. However, the objective margin in the hard negatives loss function is set as a fixed hyperparameter that ignores the semantic differences of the irrelevant image-description pairs. To address the challenge of measuring the o…
Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
Institute of Cyberspace Security, Zhejiang University of Technology（浙江工业大学网络空间安全研究院）；JQ Investments（JQ投资）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）
In this paper we focus on improving object detection performance in terms of recall. We propose a post-detection stage during which we explore the image with the objective of recovering missed detections. This exploration is performed by sampling object proposals in the image. We analyze four different strategies to perform this sampling, giving special attention to strategies that exploit spatial relations between objects. In addition, we propose a novel method to discover higher-order relations between groups of objects. Experiments on the challenging KITTI dataset show that our proposed rel…
ETIS UMR 8051；Université Paris Seine（巴黎塞纳大学）；UCP；ENSEA（国立高等电子及应用学院）；CNRS（法国国家科学研究中心）；LIGM, UMR 8049；École des Ponts（巴黎路桥学院）；UPE；C3N；Pôle Judiciaire de la Gendarmerie Nationale（国家宪兵司法中心）
In deep metric learning, the training procedure relies on sampling informative tuples. However, as the training procedure progresses, it becomes nearly impossible to sample relevant hard negative examples without proper mining strategies or generation-based methods. Recent work on hard negative generation have shown great promises to solve the mining problem. However, this generation process is difficult to tune and often leads to incorrectly labelled examples. To tackle this issue, we introduce MIRAGE, a generation-based method that relies on virtual classes entirely composed of generated exa…
Fudan University（复旦大学）；Facebook AI（Facebook人工智能研究院）；University of Maryland（马里兰大学）
Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes. In this paper, we propose Two Head Adversarial Training (THAT), a two-stream adversarial learning network that is designed to handle the large-scale many-class ImageNet dataset. The proposed method trains a network with two heads and two loss functions; one to minimize feature-space domain shift between natural and adversarial images, and one to promote high classification accuracy. This combination delivers a hardened network that achieves state of the art robust accu…
Deep Neural Networks (DNN) achieve human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of power. New hardware platforms using lower precision arithmetic achieve drastic reductions in power consumption. More recently, brain-inspired spiking neuromorphic chips have achieved even lower power consumption, on the order of milliwatts, while still offering real-time processing. However, for deploying DNNs to energy efficient neuromorphic chips the incompatibility between continuous neurons and synaptic weights of tradi…
KKA: Improving Vision Anomaly Detection through Anomaly-related Knowledge from Large Language Models
School of Computer and Artificial Intelligence of Zhengzhou University（郑州大学计算机与人工智能学院）；National Supercomputing Center In Zhengzhou（郑州国家超级计算中心）；Zhejiang University（浙江大学）
