Related papers: Meta-Point Learning and Refining for Category-Agno…

Classification models learn to generalize the associations between data samples and their target classes. However, researchers have increasingly observed that machine learning practice easily leads to systematic errors in AI applications, a…

Pursuing more complete and coherent scene understanding towards realistic vision applications drives edge detection from category-agnostic to category-aware semantic level. However, finer delineation of instance-level boundaries still…

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…

Category-level 3D pose estimation is a fundamentally important problem in computer vision and robotics, e.g. for embodied agents or to train 3D generative models. However, so far methods that estimate the category-level object pose require…

To achieve disentangled image manipulation, previous works depend heavily on manual annotation. Meanwhile, the available manipulations are limited to a pre-defined set the models were trained for. We propose a novel framework, i.e.,…

Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage them for predictions,…

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the…

Meta-learning has emerged as an efficient approach for constructing target models based on support sets. For example, the meta-learned embeddings enable the construction of target nearest-neighbor classifiers for specific tasks by pulling…

Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene…

Meta-learning aims to train models that can generalize to new tasks with limited labeled data by extracting shared features across diverse task datasets. Additionally, it accounts for prediction uncertainty during both training and…

We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose…

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually…

Animal pose estimation (APE) aims to locate the animal body parts using a diverse array of sensor and modality inputs (e.g. RGB cameras, LiDAR, infrared, IMU, acoustic and language cues), which is crucial for research across neuroscience,…

Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning…

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action within the scene. While the task is fundamental to machine perception and automated interactive…

Understanding point clouds is of great importance. Many previous methods focus on detecting salient keypoints to identity structures of point clouds. However, existing methods neglect the semantics of points selected, leading to poor…

We consider the problem of task-agnostic feature upsampling in dense prediction where an upsampling operator is required to facilitate both region-sensitive tasks like semantic segmentation and detail-sensitive tasks such as image matting.…

Absolute camera pose regressors estimate the position and orientation of a camera given the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron (MLP) head is trained using images and pose labels to embed…