As deep vision models grow increasingly complex to achieve higher performance, deployment efficiency has become a critical concern. Knowledge distillation (KD) mitigates this issue by transferring knowledge from large teacher models to compact student models. While many feature-based KD methods rely on spatial filtering to guide distillation, they typically treat all object instances uniformly, ignoring instance-level variability. Moreover, existing attention filtering mechanisms are typically heuristic or teacher-driven, rather than learned with the student. To address these limitations, we propose Learnable Instance Attention Filtering for Adaptive Detector Distillation (LIAF-KD), a novel framework that introduces learnable instance selectors to dynamically evaluate and reweight instance importance during distillation. Notably, the student contributes to this process based on its evolving learning state. Experiments on the KITTI and COCO datasets demonstrate consistent improvements, with a 2% gain on a GFL ResNet-50 student without added complexity, outperforming state-of-the-art methods.
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve the following three aspects of the contrastive pre-training pipeline: dataset noise, model initialization and the training objective. First, we propose a straightforward filtering strategy titled Complexity, Action, and Text-spotting (CAT) that significantly reduces dataset size, while achieving improved performance across zero-shot vision-language tasks. Next, we propose an approach titled Concept Distillation to leve…
University of Nottingham（诺丁汉大学）；Imperial College London（帝国理工学院）
Due to its importance in facial behaviour analysis, facial action unit (AU) detection has attracted increasing attention from the research community. Leveraging the online knowledge distillation framework, we propose the ``FANTrans" method for AU detection. Our model consists of a hybrid network of convolution and transformer blocks to learn per-AU features and to model AU co-occurrences. The model uses a pre-trained face alignment network as the feature extractor. After further transformation by a small learnable add-on convolutional subnet, the per-AU features are fed into transformer blocks…
Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；College of Information Technology, United Arab Emirates University（阿联酋大学信息技术学院）
Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledg…
Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The representation of knowledge is vital for knowledge transferring and student learning, which is generally defined in hand-crafted manners or uses the intermediate features directly. In this paper, we propose a model-agnostic meta knowledge distillation method under the teacher-student architecture for the single image super-resolution task. It provides a more flexible and accurate way t…
We present a supervised technique for learning to remove rain from images without using synthetic rain software. The method is based on a two-stage data distillation approach: 1) A rainy image is first paired with a coarsely derained version using on a simple filtering technique ("rain-to-clean"). 2) Then a clean image is randomly matched with the rainy soft-labeled pair. Through a shared deep neural network, the rain that is removed from the first image is then added to the clean image to generate a second pair ("clean-to-rain"). The neural network simultaneously learns to map both images suc…
In this paper, we present offline-to-online knowledge distillation (OOKD) for video instance segmentation (VIS), which transfers a wealth of video knowledge from an offline model to an online model for consistent prediction. Unlike previous methods that having adopting either an online or offline model, our single online model takes advantage of both models by distilling offline knowledge. To transfer knowledge correctly, we propose query filtering and association (QFA), which filters irrelevant queries to exact instances. Our KD with QFA increases the robustness of feature matching by encodin…
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
IDEAS NCBR；Warsaw University of Technology（华沙理工大学）；Gdańsk University of Technology（格但斯克理工大学）；Tooploox；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）
SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Centre for Perceptual and Interactive Intelligence（感知与交互智能研究中心）
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations. However, we observe that a key factor, i.e., the temperatures in the softmax functions for generating probabilities of both the teacher and student models, was mostly overlooked in previous methods. With properly tuned temperatures, such degradation problems of KD can be much mitigated. However, instead of rely…
Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentation
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Institute of High-Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
Horizon Robotics（地平线机器人）；University at Buffalo（布法罗大学）；Tsinghua University（清华大学）
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The outputs from the teacher network are used as soft labels for supervising the training of a new network. Recent studies \citep{muller2019does,yuan2020revisiting} revealed an intriguing property of the soft labels that making labels soft serves as a good regularization to the student network. From the perspective of statistical learning, regularization aims to reduce the variance, however how bias and variance change is n…
Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Shanghai Jiao Tong University（上海交通大学）
North South University（北南大学）；Concordia University（康考迪亚大学）
Melanoma is regarded as the most threatening among all skin cancers. There is a pressing need to build systems which can aid in the early detection of melanoma and enable timely treatment to patients. Recent methods are geared towards machine learning based systems where the task is posed as image recognition, tag dermoscopic images of skin lesions as melanoma or non-melanoma. Even though these methods show promising results in terms of accuracy, they are computationally quite expensive to train, that questions the ability of these models to be deployable in a clinical setting or memory constr…
Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection targets, making the distillation hard to balance. In this paper, we propose a conditional distillation framework to distill the desired knowledge, namely knowledge that is beneficial in terms of both classification and localization for every instance. The framework introduces a learnable conditional decoding module, which retrieves information given each target i…
University College London（伦敦大学学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Imperial College London（帝国理工学院）
State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of convolutional layers without explicitly taking into consideration the input content. Modern techniques employ deep sophisticated architectures in order to circumvent this issue. In this work, we propose a Pixel Adaptive Filtering Unit (PAFU) which introduces a differentiable kernel selection mechanism paired with a discrete, learnable and decorrelated group of kernels to allow for content-based spatial adaptation. First, we demonstrate the applicability of the technique i…
Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may enforce overly strict constraints on the student thus degrade the performance of the student model. To alleviate the above feature misalignment issue, existing works mainly focus on spatially aligning the feature maps of the teacher and the student, with pixel-wise transformation. In this paper, we newly find that aligning the feature maps between teacher and s…
Qualcomm AI Research（高通人工智能研究院）；University of Amsterdam（阿姆斯特丹大学）
This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion alignment, such as optical flow, we propose a novel knowledge distillation schema coined as Delta Distillation. In our proposal, the student learns the variations in the teacher's intermediate features over time. We demonstrate that these temporal variations can be effectively distilled due to the temporal redundancies within video frames. During inference, bot…
