Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability

Open-vocabulary object detection (OVD), detecting specific classes of objects using only their linguistic descriptions (e.g., class names) without any image samples, has garnered significant attention. However, in real-world applications, the target class concepts is often hard to describe in text and the only way to specify target objects is to provide their image examples, yet it is often challenging to obtain a good number of samples. Thus, there is a high demand from practitioners for few-shot object detection (FSOD). A natural question arises: Can the benefits of OVD extend to FSOD for object classes that are difficult to describe in text? Compared to traditional methods that learn only predefined classes (referred to in this paper as closed-set object detection, COD), can the extra cost of OVD be justified? To answer these questions, we propose a method to quantify the ``text-describability'' of object detection datasets using the zero-shot image classification accuracy with CLIP. This allows us to categorize various OD datasets with different text-describability and emprically evaluate the FSOD performance of OVD and COD methods within each category. Our findings reveal that: i) there is little difference between OVD and COD for object classes with low text-describability under equal conditions in OD pretraining; and ii) although OVD can learn from more diverse data than OD-specific data, thereby increasing the volume of training data, it can be counterproductive for classes with low-text-describability. These findings provide practitioners with valuable guidance amidst the recent advancements of OVD methods.

An Improved Method for Personalizing Diffusion Models

Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization using specific images. These methods enable generating images of specific objects based on diverse textual contexts. Our proposed approach aims to retain the model's original knowledge during new information integration, resulting in superior outcomes while necessitating less training time compared to Dreambooth and textual inversion.

SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers

Computer vision has become increasingly prevalent in solving real-world problems across diverse domains, including smart agriculture, fishery, and livestock management. These applications may not require processing many image frames per second, leading practitioners to use single board computers (SBCs). Although many lightweight networks have been developed for mobile/edge devices, they primarily target smartphones with more powerful processors and not SBCs with the low-end CPUs. This paper introduces a CNN-ViT hybrid network called SBCFormer, which achieves high accuracy and fast computation on such low-end CPUs. The hardware constraints of these CPUs make the Transformer's attention mechanism preferable to convolution. However, using attention on low-end CPUs presents a challenge: high-resolution internal feature maps demand excessive computational resources, but reducing their resolution results in the loss of local image details. SBCFormer introduces an architectural design to address this issue. As a result, SBCFormer achieves the highest trade-off between accuracy and speed on a Raspberry Pi 4 Model B with an ARM-Cortex A72 CPU. For the first time, it achieves an ImageNet-1K top-1 accuracy of around 80% at a speed of 1.0 frame/sec on the SBC. Code is available at https://github.com/xyongLu/SBCFormer.

Visual Abductive Reasoning Meets Driving Hazard Prediction: Problem Formulation and Dataset

This paper addresses the problem of predicting hazards that drivers may encounter while driving a car. We formulate it as a task of anticipating impending accidents using a single input image captured by car dashcams. Unlike existing approaches to driving hazard prediction that rely on computational simulations or anomaly detection from videos, this study focuses on high-level inference from static images. The problem needs predicting and reasoning about future events based on uncertain observations, which falls under visual abductive reasoning. To enable research in this understudied area, a new dataset named the DHPR (Driving Hazard Prediction and Reasoning) dataset is created. The dataset consists of 15K dashcam images of street scenes, and each image is associated with a tuple containing car speed, a hypothesized hazard description, and visual entities present in the scene. These are annotated by human annotators, who identify risky scenes and provide descriptions of potential accidents that could occur a few seconds later. We present several baseline methods and evaluate their performance on our dataset, identifying remaining issues and discussing future directions. This study contributes to the field by introducing a novel problem formulation and dataset, enabling researchers to explore the potential of multi-modal AI for driving hazard prediction.

Contextual Affinity Distillation for Image Anomaly Detection

Previous works on unsupervised industrial anomaly detection mainly focus on local structural anomalies such as cracks and color contamination. While achieving significantly high detection performance on this kind of anomaly, they are faced with logical anomalies that violate the long-range dependencies such as a normal object placed in the wrong position. In this paper, based on previous knowledge distillation works, we propose to use two students (local and global) to better mimic the teacher's behavior. The local student, which is used in previous studies mainly focuses on structural anomaly detection while the global student pays attention to logical anomalies. To further encourage the global student's learning to capture long-range dependencies, we design the global context condensing block (GCCB) and propose a contextual affinity loss for the student training and anomaly scoring. Experimental results show the proposed method doesn't need cumbersome training techniques and achieves a new state-of-the-art performance on the MVTec LOCO AD dataset.

That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering

Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting, specifically the one-class setting, in which we assume the availability of a set of normal (\textit{i.e.}, anomaly-free) images for training. In this paper, we consider a more challenging scenario of unsupervised AD, in which we detect anomalies in a given set of images that might contain both normal and anomalous samples. The setting does not assume the availability of known normal data and thus is completely free from human annotation, which differs from the standard AD considered in recent studies. For clarity, we call the setting blind anomaly detection (BAD). We show that BAD can be converted into a local outlier detection problem and propose a novel method named PatchCluster that can accurately detect image- and pixel-level anomalies. Experimental results show that PatchCluster shows a promising performance without the knowledge of normal data, even comparable to the SOTA methods applied in the one-class setting needing it.

RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution

Smartphones equipped with a multi-camera system comprising multiple cameras with different field-of-view (FoVs) are becoming more prevalent. These camera configurations are compatible with reference-based SR and video SR, which can be executed simultaneously while recording video on the device. Thus, combining these two SR methods can improve image quality. Recently, Lee et al. have presented such a method, RefVSR. In this paper, we consider how to optimally utilize the observations obtained, including input low-resolution (LR) video and reference (Ref) video. RefVSR extends conventional video SR quite simply, aggregating the LR and Ref inputs over time in a single bidirectional stream. However, considering the content difference between LR and Ref images due to their FoVs, we can derive the maximum information from the two image sequences by aggregating them independently in the temporal direction. Then, we propose an improved method, RefVSR++, which can aggregate two features in parallel in the temporal direction, one for aggregating the fused LR and Ref inputs and the other for Ref inputs over time. Furthermore, we equip RefVSR++ with enhanced mechanisms to align image features over time, which is the key to the success of video SR. We experimentally show that RefVSR++ outperforms RefVSR by over 1dB in PSNR, achieving the new state-of-the-art.

Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image

Despite the recent advancement in the study of removing motion blur in an image, it is still hard to deal with strong blurs. While there are limits in removing blurs from a single image, it has more potential to use multiple images, e.g., using an additional image as a reference to deblur a blurry image. A typical setting is deburring an image using a nearby sharp image(s) in a video sequence, as in the studies of video deblurring. This paper proposes a better method to use the information present in a reference image. The method does not need a strong assumption on the reference image. We can utilize an alternative shot of the identical scene, just like in video deblurring, or we can even employ a distinct image from another scene. Our method first matches local patches of the target and reference images and then fuses their features to estimate a sharp image. We employ a patch-based feature matching strategy to solve the difficult problem of matching the blurry image with the sharp reference. Our method can be integrated into pre-existing networks designed for single image deblurring. The experimental results show the effectiveness of the proposed method.

More Practical Scenario of Open-set Object Detection: Open at Category Level and Closed at Super-category Level

Open-set object detection (OSOD) has recently attracted considerable attention. It is to detect unknown objects while correctly detecting/classifying known objects. We first point out that the scenario of OSOD considered in recent studies, which considers an unlimited variety of unknown objects similar to open-set recognition (OSR), has a fundamental issue. That is, we cannot determine what to detect and what not for such unlimited unknown objects, which is necessary for detection tasks. This issue leads to difficulty with the evaluation of methods' performance on unknown object detection. We then introduce a novel scenario of OSOD, which deals with only unknown objects that share the super-category with known objects. It has many real-world applications, e.g., detecting an increasing number of fine-grained objects. This new setting is free from the above issue and evaluation difficulty. Moreover, it makes detecting unknown objects more realistic owing to the visual similarity between known and unknown objects. We show through experimental results that a simple method based on the uncertainty of class prediction from standard detectors outperforms the current state-of-the-art OSOD methods tested in the previous setting.

GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features

Current state-of-the-art methods for image captioning employ region-based features, as they provide object-level information that is essential to describe the content of images; they are usually extracted by an object detector such as Faster R-CNN. However, they have several issues, such as lack of contextual information, the risk of inaccurate detection, and the high computational cost. The first two could be resolved by additionally using grid-based features. However, how to extract and fuse these two types of features is uncharted. This paper proposes a Transformer-only neural architecture, dubbed GRIT (Grid- and Region-based Image captioning Transformer), that effectively utilizes the two visual features to generate better captions. GRIT replaces the CNN-based detector employed in previous methods with a DETR-based one, making it computationally faster. Moreover, its monolithic design consisting only of Transformers enables end-to-end training of the model. This innovative design and the integration of the dual visual features bring about significant performance improvement. The experimental results on several image captioning benchmarks show that GRIT outperforms previous methods in inference accuracy and speed.