Related papers: Annotation-Free and One-Shot Learning for Instance…

Object detection requires substantial labeling effort for learning robust models. Active learning can reduce this effort by intelligently selecting relevant examples to be annotated. However, selecting these examples properly without…

Zero-shot human-object interaction (HOI) detector is capable of generalizing to HOI categories even not encountered during training. Inspired by the impressive zero-shot capabilities offered by CLIP, latest methods strive to leverage CLIP…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a…

Previous works on video object segmentation (VOS) are trained on densely annotated videos. Nevertheless, acquiring annotations in pixel level is expensive and time-consuming. In this work, we demonstrate the feasibility of training a…

Class-agnostic object counting aims to count all objects in an image with respect to example boxes or class names, \emph{a.k.a} few-shot and zero-shot counting. In this paper, we propose a generalized framework for both few-shot and…

Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level…

Human-object interaction (HOI) synthesis is important for various applications, ranging from virtual reality to robotics. However, acquiring 3D HOI data is challenging due to its complexity and high cost, limiting existing methods to the…

In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do…

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a…

This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as…

This article investigates a data-driven approach for semantically scene understanding, without pixelwise annotation and classifier training. Our framework parses a target image with two steps: (i) retrieving its exemplars (i.e. references)…

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on…

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple…

We present a novel method for proposal free instance segmentation that can handle sophisticated object shapes which span large parts of an image and form dense object clusters with crossovers. Our method is based on predicting dense local…

Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as…

Many-shot in-context learning has recently shown promise as an alternative to finetuning, with the major advantage that the same model can be served for multiple tasks. However, this shifts the computational burden from training-time to…

Contemporary deep learning techniques have made image recognition a reasonably reliable technology. However training effective photo classifiers typically takes numerous examples which limits image recognition's scalability and…

Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero…

Object segmentation in infant's egocentric videos is a fundamental step in studying how children perceive objects in early stages of development. From the computer vision perspective, object segmentation in such videos pose quite a few…