Related papers: Unveiling the Backbone-Optimizer Coupling Bias in …

In the past five years we have observed the rise of incredibly well performing feed-forward neural networks trained supervisedly for vision related tasks. These models have achieved super-human performance on object recognition,…

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…

Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating…

Recent pre-training strategies for molecular graphs have attempted to use 2D and 3D molecular views as both inputs and self-supervised signals, primarily aligning graph-level representations. However, existing studies remain limited in…

Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples. As with the recent emergence of vision transformer (ViT) models, it remains underexplored how spurious…

Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory…

Label noise in medical image classification datasets significantly hampers the training of supervised deep learning methods, undermining their generalizability. The test performance of a model tends to decrease as the label noise rate…

The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…

Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general visual representations hinders progress. Popular protocols…

Actively planning sensor views during object reconstruction is crucial for autonomous mobile robots. An effective method should be able to strike a balance between accuracy and efficiency. In this paper, we propose a seamless integration of…

Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and pooling - with the aim of emulating simple and complex cells…

Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the…

Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon…

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…

X-ray Computed Tomography (CT) is widely used in clinical applications such as diagnosis and image-guided interventions. In this paper, we propose a new deep learning based model for CT image reconstruction with the backbone network…

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…

In recent years, the background-aware correlation filters have achie-ved a lot of research interest in the visual target tracking. However, these methods cannot suitably model the target appearance due to the exploitation of hand-crafted…

The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…

It is well observed that in deep learning and computer vision literature, visual data are always represented in a manually designed coding scheme (eg., RGB images are represented as integers ranging from 0 to 255 for each channel) when they…