Related papers: Predict-Optimize-Distill: A Self-Improving Cycle f…

Real-world scenarios pose several challenges to deep learning based computer vision techniques despite their tremendous success in research. Deeper models provide better performance, but are challenging to deploy and knowledge distillation…

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

This paper presents a novel approach, called Prototype-based Self-Distillation (ProS), for unsupervised face representation learning. The existing supervised methods heavily rely on a large amount of annotated training facial data, which…

In many situations, we need to build and deploy separate models in related environments with different data qualities. For example, an environment with strong observation equipments (e.g., intensive care units) often provides high-quality…

3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. However, image-based scene perception encounters significant challenges in achieving accurate…

We address the task of 6D multi-object pose: given a set of known 3D objects and an RGB or RGB-D input image, we detect and estimate the 6D pose of each object. We propose a new approach to 6D object pose estimation which consists of an…

Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise…

Attributes of sound inherent to objects can provide valuable cues to learn rich representations for object detection and tracking. Furthermore, the co-occurrence of audiovisual events in videos can be exploited to localize objects over the…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

3D object detection has achieved significant performance in many fields, e.g., robotics system, autonomous driving, and augmented reality. However, most existing methods could cause catastrophic forgetting of old classes when performing on…

Humans can infer 3D structure from 2D images of an object based on past experience and improve their 3D understanding as they see more images. Inspired by this behavior, we introduce SAP3D, a system for 3D reconstruction and novel view…

We propose a method to train deep networks to decompose videos into 3D geometry (camera and depth), moving objects, and their motions, with no supervision. We build on the idea of view synthesis, which uses classical camera geometry to…

Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage and computational costs, related approaches offer a promising…

This work proposes a process for efficiently training a point-wise object detector that enables localizing objects and computing their 6D poses in cluttered and occluded scenes. Accurate pose estimation is typically a requirement for robust…

Given sparse views of a 3D object, estimating their camera poses is a long-standing and intractable problem. Toward this goal, we consider harnessing the pre-trained diffusion model of novel views conditioned on viewpoints (Zero-1-to-3). We…

The ability to model the underlying dynamics of visual scenes and reason about the future is central to human intelligence. Many attempts have been made to empower intelligent systems with such physical understanding and prediction…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

3D human pose and shape recovery from a monocular RGB image is a challenging task. Existing learning based methods highly depend on weak supervision signals, e.g. 2D and 3D joint location, due to the lack of in-the-wild paired 3D…

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome…