Related papers: Dual Expert Distillation Network for Generalized Z…

Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model's prediction to ensure appropriate decisions are made by the system. Deep ensembles are…

Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak…

Knowledge distillation(KD) is a widely-used technique to train compact models in object detection. However, there is still a lack of study on how to distill between heterogeneous detectors. In this paper, we empirically find that better FPN…

Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the face that a network attends to vary by the category of an…

Recent foundation models demonstrate strong generalization capabilities in monocular depth estimation. However, directly applying these models to Full Surround Monocular Depth Estimation (FSMDE) presents two major challenges: (1) high…

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…

Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student). Several works have recently identified many scenarios where the training data may…

In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results. Thanks to the powerful representation capabilities of the deep networks, numerous previous ways can…

Staining is essential in cell imaging and medical diagnostics but poses significant challenges, including high cost, time consumption, labor intensity, and irreversible tissue alterations. Recent advances in deep learning have enabled…

Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the…

Disparity estimation is a difficult problem in stereo vision because the correspondence technique fails in images with textureless and repetitive regions. Recent body of work using deep convolutional neural networks (CNN) overcomes this…

Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data in target languages. Existing mainstream methods based on…

Zero-shot detection (ZSD), i.e., detection on classes not seen during training, is essential for real world detection use-cases, but remains a difficult task. Recent research attempts ZSD with detection models that output embeddings instead…

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Knowledge distillation is a strategy of training a student network with guide of the soft output from a teacher network. It has been a successful method of model compression and knowledge transfer. However, currently knowledge distillation…

The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural…

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD). It expands the zero-shot object detection setting by allowing the novel objects to exist in the training images and restricts the…

Iterative generative models, such as noise conditional score networks and denoising diffusion probabilistic models, produce high quality samples by gradually denoising an initial noise vector. However, their denoising process has many…

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…