Semi-Supervised Learning for FGVC With Out-of-Category Data.

Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are called for. Semi-supervised learning (SSL) techniques, acquiring knowledge from unlabeled data, provide a considerable means forward and have shown great promise for coarse-grained problems. However, exiting SSL paradigms mostly assume in-category (i.e., category-aligned) unlabeled data, which hinders their effectiveness when re-proposed on FGVC. In this paper, we put forward a novel design specifically aimed at making out-of-category data work for semi-supervised FGVC. We work off an important assumption that all fine-grained categories naturally follow a hierarchical structure (e.g., the phylogenetic tree of "Aves" that covers all bird species). It follows that, instead of operating on individual samples, we can instead predict sample relations within this tree structure as the optimization goal of SSL. Beyond this, we further introduced two strategies uniquely brought by these tree structures to achieve inter-sample consistency regularization and reliable pseudo-relation. Our experimental results reveal that (i) the proposed method yields good robustness against out-of-category data, and (ii) it can be equipped with prior arts, boosting their performance thus yielding state-of-the-art results.

Making a Bird AI Expert Work for You and Me.

As powerful as fine-grained visual classification (FGVC) is, responding your query with a bird name of "Whip-poor-will" or "Mallard" probably does not make much sense. This however commonly accepted in the literature, underlines a fundamental question interfacing AI and human - what constitutes transferable knowledge for human to learn from AI? This paper sets out to answer this very question using FGVC as a test bed. Specifically, we envisage a scenario where a trained FGVC model (the AI expert) functions as a knowledge provider in enabling average people (you and me) to become better domain experts ourselves. Assuming an AI expert trained using expert human labels, we anchor our focus on asking and providing solutions for two questions: (i) what is the best transferable knowledge we can extract from AI, and (ii) what is the most practical means to measure the gains in expertise given that knowledge? We propose to represent knowledge as highly discriminative visual regions that are expert-exclusive and instantiate it via a novel multi-stage learning framework. A human study of 15,000 trials shows our method is able to consistently improve people of divergent bird expertise to recognise once unrecognisable birds. We further propose a crude but benchmarkable metric TEMI and therefore allow future efforts in this direction to be comparable to ours without the need of large-scale human studies.

Learning Calibrated Class Centers for Few-Shot Classification by Pair-Wise Similarity.

Metric-based methods achieve promising performance on few-shot classification by learning clusters on support samples and generating shared decision boundaries for query samples. However, existing methods ignore the inaccurate class center approximation introduced by the limited number of support samples, which consequently leads to biased inference. Therefore, in this paper, we propose to reduce the approximation error by class center calibration. Specifically, we introduce the so-called Pair-wise Similarity Module (PSM) to generate calibrated class centers adapted to the query sample by capturing the semantic correlations between the support and the query samples, as well as enhancing the discriminative regions on support representation. It is worth noting that the proposed PSM is a simple plug-and-play module and can be inserted into most metric-based few-shot learning models. Through extensive experiments in metric-based models, we demonstrate that the module significantly improves the performance of conventional few-shot classification methods on four few-shot image classification benchmark datasets. Codes are available at: https://github.com/PRIS-CV/Pair-wise-Similarity-module.

Progressive Learning of Category-Consistent Multi-Granularity Features for Fine-Grained Visual Classification.

Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works are mainly part-driven (either explicitly or implicitly), with the assumption that fine-grained information naturally rests within the parts. In this paper, we take a different stance, and show that part operations are not strictly necessary - the key lies with encouraging the network to learn at different granularities and progressively fusing multi-granularity features together. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a consistent block convolution that encourages the network to learn the category-consistent features at specific granularities. We evaluate on several standard FGVC benchmark datasets, and demonstrate the proposed method consistently outperforms existing alternatives or delivers competitive results. Codes are available at https://github.com/PRIS-CV/PMG-V2.

Arsenic induces transgenerational behavior disorders in Caenorhabditis elegans and its underlying mechanisms.

The present study aimed to identify the effects of arsenic on behaviors in Caenorhabditis elegans (C. elegans) and the transgenerational effects. The synchronized C. elegans (P generation) were exposed to 0, 0.2, 1.0, and 5.0 mM NaAsO2 and the subsequent generations (F1 and F2) were maintained on fresh nematode growth medium (NGM). The behaviors and growth were recorded at 0, 12, 24, 36, 48, 60, and 72 h post synchronization. The results demonstrated that arsenic affected various indicators regarding the behavior (head thrash, body bend, movement speed, wavelength, amplitude and so on) and in general the effects started to accumulate from 24 h and lasted throughout the exposure. The behavior impairments were transgenerational with varying patterns, amongst the head thrash and body bend responded most sensitively though the responses gradually declined across generations. Arsenic exposure inhibited the growth (body length, body width, and body area) in P C. elegans from 24 h to 60 h, however there was no difference between treatments groups and the control at 72 h. Arsenic led to a dose-dependent degeneration of dopaminergic neurons in C. elegans, and inhibition of BAS-1 and CAT-2 expressions. The expressions of GCS-1, GSS-1, and SKN-1 were induced by arsenic exposure. Overall, chronic arsenic exposure impaired the behaviors and there were transgenerational effects. The head thrash and body bend responded most sensitively. Arsenic induced behavioral disorders might be attributed to degeneration of dopaminergic neurons which was associated with oxidative stress.